Search Results for author:
Found 30 papers, 16 papers with code
On the Efficiency and Robustness of Vibration-based Foundation Models for IoT Sensing: A Case Study
This paper demonstrates the potential of vibration-based Foundation Models (FMs), pre-trained with unlabeled sensing data, to improve the robustness of run-time inference in (a class of) IoT applications.
DevBench: A Comprehensive Benchmark for Software Development
Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities.
Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents
The challenges and costs of collecting realistic interactive logs for data analysis hinder the quantitative evaluation of Large Language Model (LLM) agents in this task.
Delving into the Trajectory Long-tail Distribution for Muti-object Tracking
In this study, we pioneer an exploration into the distribution patterns of tracking data and identify a pronounced long-tail distribution issue within existing MOT datasets.
A Survey on Knowledge Distillation of Large Language Models
In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral.
SudokuSens: Enhancing Deep Learning Robustness for IoT Sensing Applications using a Generative Approach
To incorporate sufficient diversity into the IoT training data, one therefore needs to consider a combinatorial explosion of training cases that are multiplicative in the number of objects considered and the possible environmental conditions in which such objects may be encountered.
SAMF: Small-Area-Aware Multi-focus Image Fusion for Object Detection
Existing multi-focus image fusion (MFIF) methods often fail to preserve the uncertain transition region and detect small focus areas within large defocused regions accurately.
Stateful Large Language Model Serving with Pensieve
Consequently, when LLMs are used in the common setting of multi-turn conversations, a growing log of the conversation history must be processed alongside any request by the serving system at each turn, resulting in repeated history processing.
FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space
Existing multimodal contrastive frameworks mostly rely on the shared information between sensory modalities, but do not explicitly consider the exclusive modality information that could be critical to understanding the underlying sensing physics.
An Investigation of LLMs' Inefficacy in Understanding Converse Relations
Our ConvRE features two tasks, Re2Text and Text2Re, which are formulated as multi-choice question answering to evaluate LLMs' ability to determine the matching between relations and associated text.
A Novel Spatial-Temporal Variational Quantum Circuit to Enable Deep Learning on NISQ Devices
The results of the evaluation on the standard dataset for binary classification show that ST-VQC can achieve over 30% accuracy improvement compared with existing VQCs on actual quantum computers.
Causal Document-Grounded Dialogue Pre-training
To tackle this issue, we are the first to present a causally-complete dataset construction strategy for building million-level DocGD pre-training corpora.
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
Our emphasis on database values highlights the new challenges of dirty database contents, external knowledge between NL questions and database contents, and SQL efficiency, particularly in the context of massive databases.
Ranked #1 on
Text-To-SQL
on BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)
(Execution Accurarcy (Human) metric)
QuMoS: A Framework for Preserving Security of Quantum Machine Learning Model
We further developed a reinforcement learning-based security engine, which can automatically optimize the model design under the distributed setting, such that a good trade-off between model performance and security can be made.
Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing
Recently, the pre-trained text-to-text transformer model, namely T5, though not specialized for text-to-SQL parsing, has achieved state-of-the-art performance on standard benchmarks targeting domain generalization.
Ranked #4 on
Semantic Parsing
on spider
Detection of Groups with Biased Representation in Ranking
We propose efficient search algorithms for two different fairness measures: global representation bounds, and proportional representation.
A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions
In recent years, deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output SQL query.
NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers
In this work, we propose a new fuzz testing approach for finding bugs in deep-learning compilers.
An AIoT-enabled Autonomous Dementia Monitoring System
The system mainly implements two functions based on the activity inference of the sensor data, which are real time abnormal activity monitoring and trend prediction of disease related activities.
Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
Our algorithm estimates the AME, a quantity that measures the expected (average) marginal effect of adding a data point to a subset of the training data, sampled from a given distribution.
Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders
Inspired by total correlation in information theory, we propose the Information-Theoretic Variational Graph Auto-Encoder (InfoVGAE) that learns to project both users and content items (e. g., posts that represent user views) into an appropriate disentangled latent space.
Scalable Graph Neural Networks for Heterogeneous Graphs
Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data.
Ranked #20 on
Node Property Prediction
on ogbn-mag
Deep Compressive Offloading: Speeding Up Neural Network Inference by Trading Edge Computation for Network Latency
With comprehensive evaluations, our system can consistently reduce end-to-end latency by 2× to 4× with 1% accuracy loss, compared to state-of-the-art neural network offloading systems.
Scheduling Real-time Deep Learning Services as Imprecise Computations
The paper presents an efficient real-time scheduling algorithm for intelligent real-time edge services, defined as those that perform machine intelligence tasks, such as voice recognition, LIDAR processing, or machine vision, on behalf of local embedded devices that are themselves unable to support extensive computations.
DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition
Finally, the DTG-Net is evaluated in two ways: (i) the self-supervised DTG-Net to pre-train the supervised action recognition models with only unlabeled videos; (ii) the supervised DTG-Net to be jointly trained with the supervised action networks in an end-to-end way.
Hierarchical Overlapping Belief Estimation by Structured Matrix Factorization
In the synthetic dataset, our model reduces error by 40%.
Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs.
Ranked #35 on
Node Classification
on Cora
STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks
IoT applications, however, often measure physical phenomena, where the underlying physics (such as inertia, wireless signal propagation, or the natural frequency of oscillation) are fundamentally a function of signal frequencies, offering better features in the frequency domain.
Supporting Very Large Models using Automatic Dataflow Graph Partitioning
This paper presents Tofu, a system that partitions very large DNN models across multiple GPU devices to reduce per-GPU memory footprint.
Unifying Data, Model and Hybrid Parallelism in Deep Learning via Tensor Tiling
We present this automatic tiling in a new system, SoyBean, that can act as a backend for Tensorflow, MXNet, and others.
